© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44485
    Prev
    Next
    INDEX
    Explanations

    conditional code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    "log
    -0.07
    Ïģγο
    -0.07
    implicit
    -0.07
    tock
    -0.06
    磨
    -0.06
     inert
    -0.06
     implicit
    -0.06
    ÎŃÏģγ
    -0.06
    Implicit
    -0.06
    .nodeType
    -0.06
    POSITIVE LOGITS
    æ£ĢæµĭåĪ°
    0.08
    è¿Ľè¡ĮåĪĨç±»
    0.08
    æľīæĿ¡ä»¶
    0.08
    èĩªå·±æĺ¯
    0.08
    -exclusive
    0.08
    çī¹æ®Ĭ
    0.07
     SPECIAL
    0.07
    åħĪæĿ¥
    0.07
     conditions
    0.07
    åħĪçľĭ
    0.07
    Activations Density 0.037%

    No Known Activations